Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    -g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numero
    -0.07
    ㉲
    -0.07
    ি
    -0.07
    ете
    -0.07
    宠
    -0.07
    �
    -0.06
     biết
    -0.06
    慎
    -0.06
     آ
    -0.06
    當您
    -0.06
    POSITIVE LOGITS
     linen
    0.07
     ah
    0.07
    �
    0.07
     DID
    0.07
     oran
    0.07
    @Module
    0.06
    щин
    0.06
    _DATE
    0.06
    /mark
    0.06
    short
    0.06
    Act Density 0.005%

    No Known Activations